Efficient Unlearning for Spatio-temporal Graph (Student Abstract)

Machine unlearning is becoming increasingly important as deep models become more prevalent, particularly when there are frequent requests to remove the influence of specific training data due to privacy concerns or erroneous sensing signals. Spatial-temporal Graph Neural Networks, in particular, have been widely adopted in real-world applications that demand efficient unlearning, yet research in this area remains in its early stages. In this paper, we introduce STEPS, a framework specifically designed to address the challenges of spatio-temporal graph unlearning. Our results demonstrate that STEPS not only ensures data continuity and integrity but also significantly reduces the time required for unlearning, while minimizing the accuracy loss in the new model compared to a model with 0% unlearning.

Authors

• Qiming Guo Texas A&M University-Corpus Christi
• Chen Pan
• Hua Zhang Texas A&M University-Corpus Christi
• Wenlu Wang Texas A&M University-Corpus Christi

Keywords

No keywords are indexed for this paper.